Training in progress, step 2150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4cdedefbc08e52a106dd1cda00ce357a19a652b9800eb784f0f1307cc43d1f
+oid sha256:6b6cad65a1239e0e03962e7f4ef559abd941989cf40db0a80d0189112e42eb72
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fb08110ee38613bcd192ba1aba3314492e8466845e6293f310b5afb02a7b1e
+oid sha256:2b8a70c19523d8c6e08995eab7545028af88fed635908dfc05a7946675d3475a
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3700e8b436e0bb6d4386467f582113bce4defdd80381438810f0ff98ab850a
+oid sha256:f9759af3432ea363e3c64dd28f0228b81e57792402129de6cb79a2e5033a37e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:823f545a614848455ef557579867553ca1e0ed28d34695c57c4a484f3da883fe
+oid sha256:2e6aaab334f3a9481d30ef9495cbe830ba9fac2b9efdeee34a635582fea7ec27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016924044886549167,
+  "epoch": 0.017123151296979156,
   "eval_steps": 500,
-  "global_step": 2125,
+  "global_step": 2150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2551,6 +2551,42 @@
       "reward_std": 0.307485481351614,
       "rewards/custom_reward_simplified_v7_dblog": 0.7875,
       "step": 2120
+    },
+    {
+      "completion_length": 685.39375,
+      "epoch": 0.016963866168635166,
+      "grad_norm": 0.30204537510871887,
+      "kl": 0.018967814440838993,
+      "learning_rate": 1.9030116872178317e-07,
+      "loss": 0.0008,
+      "reward": 0.803125,
+      "reward_std": 0.3279333204030991,
+      "rewards/custom_reward_simplified_v7_dblog": 0.803125,
+      "step": 2130
+    },
+    {
+      "completion_length": 674.49375,
+      "epoch": 0.01704350873280716,
+      "grad_norm": 0.012012571096420288,
+      "kl": 0.02170075795147568,
+      "learning_rate": 1.7663118943294367e-07,
+      "loss": 0.0009,
+      "reward": 0.703125,
+      "reward_std": 0.2257047951221466,
+      "rewards/custom_reward_simplified_v7_dblog": 0.703125,
+      "step": 2140
+    },
+    {
+      "completion_length": 694.63125,
+      "epoch": 0.017123151296979156,
+      "grad_norm": 0.01635037176311016,
+      "kl": 0.02094450539443642,
+      "learning_rate": 1.6345268662752904e-07,
+      "loss": 0.0008,
+      "reward": 0.7125,
+      "reward_std": 0.2917635254561901,
+      "rewards/custom_reward_simplified_v7_dblog": 0.7125,
+      "step": 2150
     }
   ],
   "logging_steps": 10,